© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13492
    Prev
    Next
    INDEX
    Explanations

    references to friendships and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "friends" or "friend."

    np_acts-logits-general · gemini-2.0-flash

    friends / friend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.52
    JsonInclude
    -0.51
     AssemblyVersion
    -0.49
    ỏa
    -0.49
    Quais
    -0.49
    }")]
    -0.48
    Vey
    -0.48
     
    -0.47
    }>;
    -0.47
    ])):
    -0.47
    POSITIVE LOGITS
     friends
    1.09
    friend
    1.05
     friend
    1.05
    Friend
    1.03
     Friend
    1.02
     Friends
    1.01
     FRIEND
    0.99
    Friends
    0.98
    friends
    0.94
    FRIEND
    0.94
    Activations Density 0.043%

    No Known Activations